Exploring Fine-Grained Sparsity in Convolutional Neural Networks for Efficient Inference
Neural networks contain considerable redundant computation, which drags down the inference efficiency and hinders the deployment on resource-limited devices. In this paper, we study the sparsity in convolutional neural networks and propose a generic sparse mask mechanism to improve the inference eff...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 4 vom: 09. Apr., Seite 4474-4493
|
|---|
| 1. Verfasser: |
Wang, Longguang
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Guo, Yulan,
Dong, Xiaoyu,
Wang, Yingqian,
Ying, Xinyi,
Lin, Zaiping,
An, Wei |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|